Multi-robot patrolling is known to be challenging, especially in a decentralized manner. The state-of-the-art de-centralized approaches are either suboptimal or usually require exchange of information that would potentially limit their scalability. This paper presents a novel decentralized approach of high scalability and robustness to multi- UAV persistent surveillance. Our solution decentralizes a cyclic strategy while considering communication constraints. We give a theoretical derivation of the decentralized algorithm with convergence analysis. In addition, we consider practical issues such as motion constraints and potential livelocks in our implementation. The proposed approach is extensively tested and analyzed in a medium-fidelity swarm simulator to minimize the gap between simulation and real experiments.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Highly Scalable, Robust and Decentralized Approach for Multi-UAV Persistent Surveillance


    Beteiligte:
    Cao, Jiawei (Autor:in) / Leong, Wai Lun (Autor:in) / Huat Teo, Rodney Swee (Autor:in)


    Erscheinungsdatum :

    04.06.2024


    Format / Umfang :

    4736561 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Multi Agent Reinforcement Learning Based Decentralized Swarm UAV Control Framework for Persistent Surveillance

    Kaliappan, Vishnu Kumar / Nguyen, Tuan Anh / Jeon, Sang Woo et al. | Springer Verlag | 2022





    Robust, Highly Scalable Solar Array System

    Francis, William H. / Davis, Bruce / Lake, Mark | AIAA | 2016